Overview

AI Prompt Logger Analytics Tool

A comprehensive personal productivity analytics tool for tracking and analyzing your interactions
with AI tools like ChatGPT, GitHub Copilot, and Gemini.

## Overview

This tool helps you:

- Track your daily AI tool usage

- Analyze satisfaction levels across different tools

- Identify patterns in your prompting behavior

- Generate insights to improve your AI productivity

## Files Included

- `ai_prompt_log.csv` - Sample data file with the required format

- `ai_prompt_logger.py` - Main analysis script (standalone Python)

- `ai_prompt_logger.ipynb` - Jupyter notebook version with interactive analysis

- `prompt_logger_cli.py` - Command-line tool for adding new entries

- `[Link]` - This file

## Data Format

The CSV file should contain these columns:

| Column | Description | Example |

| -------------- | ------------------------- | ----------------------------------------- |

| `date` | Date in YYYY-MM-DD format | 2025-07-29 |

| `prompt_type` | Category of task | coding, writing, debugging, documentation |

| `goal` | Brief description | "build resume parser" |

| `satisfaction` | Rating from 1-5 |4 |

## Getting Started

### Prerequisites

Install required Python packages:

```bash

pip install pandas numpy matplotlib seaborn

```

### Option 1: Run the Python Script

```bash

python ai_prompt_logger.py

```

This will:

- Load and clean your data

- Perform basic analysis

- Generate comprehensive visualizations

- Export a summary report

### Option 2: Use the Jupyter Notebook

1. Launch Jupyter:
```bash

jupyter notebook ai_prompt_logger.ipynb

```

2. Run cells step by step for interactive analysis

### Option 3: Add New Entries with CLI Tool

```bash

# Interactive mode

python prompt_logger_cli.py

# Quick add mode

python prompt_logger_cli.py --add

```

## Features

### 1. Data Cleaning & Validation

- Converts dates to proper datetime format

- Identifies and warns about missing values

- Validates satisfaction scores (1-5 range)

### 2. Basic Analysis

- Total prompt count per tool

- Average satisfaction per tool

- Frequency of each prompt type

- Overall statistics and trends

#### Time-based Trends

- Line chart of satisfaction scores over time

- Bar plot of daily prompt counts

- Trend analysis with regression lines

#### Tool-wise Analysis

- Box plot showing satisfaction distribution by tool

- Horizontal bar chart of tool usage frequency

- Performance comparison across tools

#### Prompt Type Analysis

- Calendar-style heatmap of prompt types by date

- Satisfaction heatmap by prompt type and tool

- Activity pattern analysis

#### Rating Distribution

- Pie chart of satisfaction score distribution

- Histogram with statistical overlays

- Mean and median indicators

### 4. Insights Generated

- Best and worst performing tools

- Most and least used tools

- Daily productivity patterns

- Trend analysis and recommendations

### 5. Export Options

- Comprehensive text report

- All visualizations as plots

- Statistical summaries

## Customization

### Adding New Tools

Edit the `tools` list in `prompt_logger_cli.py`:

```python

[Link] = ['ChatGPT', 'Gemini', 'Copilot', 'Claude', 'YourNewTool']

```

### Adding New Prompt Types

Edit the `prompt_types` list:

```python

self.prompt_types = ['coding', 'writing', 'debugging', 'documentation', 'research', 'creative',

```

### Modifying Visualizations

- Change color schemes

- Modify plot types

- Add new charts

- Adjust figure sizes

## Sample Output

The tool generates:

```

BASIC ANALYSIS

==================================================

Total prompts per tool:

Copilot: 8 prompts

ChatGPT: 8 prompts

Gemini: 6 prompts

Average satisfaction per tool:

Copilot: 4.50 ± 0.53 (n=8)

ChatGPT: 4.25 ± 0.46 (n=8)

Gemini: 2.67 ± 0.52 (n=6)

Prompt types used:

coding: 8 times

writing: 5 times

debugging: 5 times

documentation: 4 times
 KEY INSIGHTS

==================================================

Best performing tool: Copilot (avg satisfaction: 4.50)

Most used tool: Copilot (8 prompts)

Most common activity: coding (8 times)

Overall satisfaction: 3.77 ± 0.87

```

## Usage Tips

1. **Daily Logging**: Make it a habit to log your AI interactions daily for accurate trends

2. **Consistent Categories**: Use consistent prompt types and tool names

3. **Honest Ratings**: Rate satisfaction honestly to get meaningful insights

4. **Regular Analysis**: Run the analysis weekly to track improvements

5. **Goal Descriptions**: Keep goals brief but descriptive for better categorization

## Future Enhancements

Potential improvements you could add:

- Web interface using Streamlit or Flask

- Integration with AI tool APIs for automatic logging

- Machine learning models for prompt success prediction

- Export to PDF reports with matplotlib

- Database storage instead of CSV

- Real-time dashboard updates

## License

This tool is provided as-is for personal productivity tracking. Feel free to modify and enhance
according to your needs.
## Troubleshooting

### Common Issues

1. **"CSV file not found"**

- Make sure `ai_prompt_log.csv` exists in the same directory

- Run the CLI tool to create your first entries

2. **"Module not found" errors**

- Install required packages: `pip install pandas numpy matplotlib seaborn`

3. **Date parsing errors**

- Ensure dates are in YYYY-MM-DD format

- Check for empty or malformed date entries

4. **Visualization not showing**

- For Jupyter notebooks, use `%matplotlib inline`

- For scripts, ensure you have a display available

### Getting Help

If you encounter issues:

1. Check the error messages for missing dependencies

2. Verify your CSV file format matches the expected structure

3. Make sure you have sufficient data (at least a few entries) for meaningful analysis
---

Happy analyzing! Track your AI productivity and optimize your interactions for better results.